Skip to content
ImagesFree

Image Physics: How to Spot AI-Generated Photos

An article explaining how physics-based image analysis – perspective, vanishing points, mirror reflections and shadows – reveals manipulation and AI-generated images, with a brief history of photo manipulation and Hany Farid's digital forensics research.

Image generation

Source previews

These example images come from the original source. DROPIDEA has not independently tested these examples; results depend on the model and settings.

Ready to personalize

Your prompt

English

Replace the red variables with your information. Copy the full prompt and use it with your preferred agent.

TXT MD English version
Getting the physics right is much trickier even for AI. That's exactly what caught my attention when I analyzed some images last spring. Today I came across a very interesting article that discusses exactly this issue – the physics of an image and the geometry of a scene. Here's a brief summary. The history of photo manipulation is as old as photography itself. A famous portrait of Abraham Lincoln actually shows Lincoln's head superimposed onto the body of politician John Calhoun. Stalin famously airbrushed political opponents out of photographs. And two girls from Yorkshire convinced countless people – including Arthur Conan Doyle – that their photographs of fairies were genuine. But how can we tell whether a digital image is actually real? Digital forensics expert Hany Farid realized that whenever a computer creates new pixels by extrapolating from existing ones, it leaves behind detectable traces – statistical correlations between pixels. The challenge, therefore, was not to "prove" that an image was authentic, but to identify the traces left by different types of manipulation. Eventually, he concluded that the answer lies in physics. Today, billions of people have access to AI systems capable of producing photorealistic images from almost any prompt within seconds. Early AI-generated images were often easy to spot because they lacked subtle statistical signatures present in real photographs, such as sensor noise or lens artifacts. However, modern image generators have become remarkably good at learning and reproducing these patterns, even adding realistic imperfections to mimic camera-generated images. Physics, however, is a different story. When analyzing an image, it's always worth asking a simple question: Does this scene obey the laws of the real world? For example, in a genuine photograph, lines that are parallel in reality should converge toward the same vanishing point. Likewise, lines connecting points on an object with the corresponding points in its mirror reflection should also converge consistently according to the rules of perspective. Shadows can also reveal inconsistencies. Because the Sun is so far away, its rays are effectively parallel when they reach the Earth's surface, which places strict constraints on the direction and behavior of shadows. "Generative AI doesn't know about physics, doesn't know about geometry, and it does all kinds of crazy shit." Source (Science): https://t.co/Kt5jJcufpm
Preview results

Your prompt

Getting the physics right is much trickier even for AI. That's exactly what caught my attention when I analyzed some images last spring. Today I came across a very interesting article that discusses exactly this issue – the physics of an image and the geometry of a scene. Here's a brief summary. The history of photo manipulation is as old as photography itself. A famous portrait of Abraham Lincoln actually shows Lincoln's head superimposed onto the body of politician John Calhoun. Stalin famously airbrushed political opponents out of photographs. And two girls from Yorkshire convinced countless people – including Arthur Conan Doyle – that their photographs of fairies were genuine. But how can we tell whether a digital image is actually real? Digital forensics expert Hany Farid realized that whenever a computer creates new pixels by extrapolating from existing ones, it leaves behind detectable traces – statistical correlations between pixels. The challenge, therefore, was not to "prove" that an image was authentic, but to identify the traces left by different types of manipulation. Eventually, he concluded that the answer lies in physics. Today, billions of people have access to AI systems capable of producing photorealistic images from almost any prompt within seconds. Early AI-generated images were often easy to spot because they lacked subtle statistical signatures present in real photographs, such as sensor noise or lens artifacts. However, modern image generators have become remarkably good at learning and reproducing these patterns, even adding realistic imperfections to mimic camera-generated images. Physics, however, is a different story. When analyzing an image, it's always worth asking a simple question: Does this scene obey the laws of the real world? For example, in a genuine photograph, lines that are parallel in reality should converge toward the same vanishing point. Likewise, lines connecting points on an object with the corresponding points in its mirror reflection should also converge consistently according to the rules of perspective. Shadows can also reveal inconsistencies. Because the Sun is so far away, its rays are effectively parallel when they reach the Earth's surface, which places strict constraints on the direction and behavior of shadows. "Generative AI doesn't know about physics, doesn't know about geometry, and it does all kinds of crazy shit." Source (Science): https://t.co/Kt5jJcufpm

What you get

  • A complete article covering the history of photo manipulation and the fundamentals of physics-based analysis.
  • An explanation of detection techniques: vanishing points, perspective rules, mirror reflections and shadow direction.
  • Insight into how AI image generators have evolved to mimic camera statistical signatures.
  • A direct quote and a preserved link to the original source.

Use cases

  • Writing awareness posts about deepfakes and AI-generated images.
  • Preparing lessons or workshops on image verification and digital forensics.
  • Creating simplified educational content about perspective and shadows in photography.
  • Using the article as a reference in technology blogs and science journalism.

How to use

  • Read the full article to grasp the principle of analyzing an image's physics and a scene's geometry.
  • Review the historical examples of photo manipulation to frame the topic in context.
  • Apply the article's analytical questions to images you need to verify: perspective, vanishing points, mirror reflections and shadows.
  • Use the link at the end of the article to consult the original Science source.
  • Cite the article when writing awareness content about detecting AI-generated images.

Related prompts